Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380136500> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4380136500 abstract "The federated learning (FL) technique was developed to mitigate data privacy issues in the traditional machine learning paradigm. While FL ensures that a user's data always remain with the user, the gradients are shared with the centralized server to build the global model. This results in privacy leakage, where the server can infer private information from the shared gradients. To mitigate this flaw, the next-generation FL architectures proposed encryption and anonymization techniques to protect the model updates from the server. However, this approach creates other challenges, such as malicious users sharing false gradients. Since the gradients are encrypted, the server is unable to identify rogue users. To mitigate both attacks, this paper proposes a novel FL algorithm based on a fully homomorphic encryption (FHE) scheme. We develop a distributed multi-key additive homomorphic encryption scheme that supports model aggregation in FL. We also develop a novel aggregation scheme within the encrypted domain, utilizing users' non-poisoning rates, to effectively address data poisoning attacks while ensuring privacy is preserved by the proposed encryption scheme. Rigorous security, privacy, convergence, and experimental analyses have been provided to show that FheFL is novel, secure, and private, and achieves comparable accuracy at reasonable computational cost." @default.
- W4380136500 created "2023-06-10" @default.
- W4380136500 creator A5009232291 @default.
- W4380136500 creator A5021724967 @default.
- W4380136500 creator A5026556562 @default.
- W4380136500 creator A5080175512 @default.
- W4380136500 creator A5085881376 @default.
- W4380136500 date "2023-06-08" @default.
- W4380136500 modified "2023-09-25" @default.
- W4380136500 title "FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users" @default.
- W4380136500 doi "https://doi.org/10.48550/arxiv.2306.05112" @default.
- W4380136500 hasPublicationYear "2023" @default.
- W4380136500 type Work @default.
- W4380136500 citedByCount "0" @default.
- W4380136500 crossrefType "posted-content" @default.
- W4380136500 hasAuthorship W4380136500A5009232291 @default.
- W4380136500 hasAuthorship W4380136500A5021724967 @default.
- W4380136500 hasAuthorship W4380136500A5026556562 @default.
- W4380136500 hasAuthorship W4380136500A5080175512 @default.
- W4380136500 hasAuthorship W4380136500A5085881376 @default.
- W4380136500 hasBestOaLocation W43801365001 @default.
- W4380136500 hasConcept C123201435 @default.
- W4380136500 hasConcept C134306372 @default.
- W4380136500 hasConcept C147977885 @default.
- W4380136500 hasConcept C148730421 @default.
- W4380136500 hasConcept C158338273 @default.
- W4380136500 hasConcept C166501710 @default.
- W4380136500 hasConcept C31258907 @default.
- W4380136500 hasConcept C33923547 @default.
- W4380136500 hasConcept C38652104 @default.
- W4380136500 hasConcept C41008148 @default.
- W4380136500 hasConcept C77618280 @default.
- W4380136500 hasConcept C99221444 @default.
- W4380136500 hasConceptScore W4380136500C123201435 @default.
- W4380136500 hasConceptScore W4380136500C134306372 @default.
- W4380136500 hasConceptScore W4380136500C147977885 @default.
- W4380136500 hasConceptScore W4380136500C148730421 @default.
- W4380136500 hasConceptScore W4380136500C158338273 @default.
- W4380136500 hasConceptScore W4380136500C166501710 @default.
- W4380136500 hasConceptScore W4380136500C31258907 @default.
- W4380136500 hasConceptScore W4380136500C33923547 @default.
- W4380136500 hasConceptScore W4380136500C38652104 @default.
- W4380136500 hasConceptScore W4380136500C41008148 @default.
- W4380136500 hasConceptScore W4380136500C77618280 @default.
- W4380136500 hasConceptScore W4380136500C99221444 @default.
- W4380136500 hasLocation W43801365001 @default.
- W4380136500 hasOpenAccess W4380136500 @default.
- W4380136500 hasPrimaryLocation W43801365001 @default.
- W4380136500 hasRelatedWork W2037113620 @default.
- W4380136500 hasRelatedWork W2147708684 @default.
- W4380136500 hasRelatedWork W2543408143 @default.
- W4380136500 hasRelatedWork W2559972107 @default.
- W4380136500 hasRelatedWork W3004172225 @default.
- W4380136500 hasRelatedWork W4205670975 @default.
- W4380136500 hasRelatedWork W4308465478 @default.
- W4380136500 hasRelatedWork W4309969708 @default.
- W4380136500 hasRelatedWork W4313046019 @default.
- W4380136500 hasRelatedWork W4321510660 @default.
- W4380136500 isParatext "false" @default.
- W4380136500 isRetracted "false" @default.
- W4380136500 workType "article" @default.